[PATCH rdma-next] RDMA/irdma: Check MR contiguity before PBLE alloc

[Jacob Moroni <jmoroni@google.com>]

The original logic would attempt to allocate PBLEs, then would
check whether the region was contiguous _after_, and if so,
would free the PBLEs and use a direct mapping instead.

These unnecessary temporary PBLE allocations can technically
fail (PBLEs are a finite resource), which can cause an MR
registration failure even if the region is contiguous and
should have succeeded.

Fix this by checking whether the region is contiguous before
allocating any PBLEs, and use the ib_umem_is_contiguous
helper while we're at it.

Ring MRs still have their own logic. That will be addressed next.

Signed-off-by: Jacob Moroni <jmoroni@google.com>
---
 drivers/infiniband/hw/irdma/verbs.c | 50 +++--------------------------
 drivers/infiniband/hw/irdma/verbs.h |  1 +
 2 files changed, 5 insertions(+), 46 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 71d7ae7baa47..7ea256e640fa 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -2917,42 +2917,6 @@ static bool irdma_check_mem_contiguous(u64 *arr, u32 npages, u32 pg_size)
 	return true;
 }
 
-/**
- * irdma_check_mr_contiguous - check if MR is physically contiguous
- * @palloc: pbl allocation struct
- * @pg_size: page size
- */
-static bool irdma_check_mr_contiguous(struct irdma_pble_alloc *palloc,
-				      u32 pg_size)
-{
-	struct irdma_pble_level2 *lvl2 = &palloc->level2;
-	struct irdma_pble_info *leaf = lvl2->leaf;
-	u64 *arr = NULL;
-	u64 *start_addr = NULL;
-	int i;
-	bool ret;
-
-	if (palloc->level == PBLE_LEVEL_1) {
-		arr = palloc->level1.addr;
-		ret = irdma_check_mem_contiguous(arr, palloc->total_cnt,
-						 pg_size);
-		return ret;
-	}
-
-	start_addr = leaf->addr;
-
-	for (i = 0; i < lvl2->leaf_cnt; i++, leaf++) {
-		arr = leaf->addr;
-		if ((*start_addr + ((u64)i * pg_size * PBLE_PER_PAGE)) != *arr)
-			return false;
-		ret = irdma_check_mem_contiguous(arr, leaf->cnt, pg_size);
-		if (!ret)
-			return false;
-	}
-
-	return true;
-}
-
 /**
  * irdma_setup_pbles - copy user pg address to pble's
  * @rf: RDMA PCI function
@@ -3417,22 +3381,13 @@ static int irdma_reg_user_mr_type_mem(struct irdma_mr *iwmr, int access,
 	u8 lvl;
 	int err;
 
-	lvl = iwmr->page_cnt != 1 ? PBLE_LEVEL_1 | PBLE_LEVEL_2 : PBLE_LEVEL_0;
+	lvl = iwmr->is_contig ? PBLE_LEVEL_0 : PBLE_LEVEL_1 | PBLE_LEVEL_2;
 	iwmr->access = access;
 
 	err = irdma_setup_pbles(iwdev->rf, iwmr, lvl);
 	if (err)
 		return err;
 
-	if (lvl) {
-		err = irdma_check_mr_contiguous(&iwpbl->pble_alloc,
-						iwmr->page_size);
-		if (err) {
-			irdma_free_pble(iwdev->rf->pble_rsrc, &iwpbl->pble_alloc);
-			iwpbl->pbl_allocated = false;
-		}
-	}
-
 	if (create_stag) {
 		stag = irdma_create_stag(iwdev);
 		if (!stag) {
@@ -3487,6 +3442,8 @@ static struct irdma_mr *irdma_alloc_iwmr(struct ib_umem *region,
 	pgsz_bitmap = (reg_type == IRDMA_MEMREG_TYPE_MEM) ?
 		iwdev->rf->sc_dev.hw_attrs.page_size_cap : SZ_4K;
 
+	iwmr->is_contig = ib_umem_is_contiguous(region);
+	/* Call best_pgsz after is_contiguous to restore correct umem->iova. */
 	iwmr->page_size = ib_umem_find_best_pgsz(region, pgsz_bitmap, virt);
 	if (unlikely(!iwmr->page_size)) {
 		kfree(iwmr);
@@ -3846,6 +3803,7 @@ static int irdma_rereg_mr_trans(struct irdma_mr *iwmr, u64 start, u64 len,
 	iwmr->region = region;
 	iwmr->ibmr.iova = virt;
 	iwmr->ibmr.pd = pd;
+	iwmr->is_contig = ib_umem_is_contiguous(region);
 	iwmr->page_size = ib_umem_find_best_pgsz(region,
 				iwdev->rf->sc_dev.hw_attrs.page_size_cap,
 				virt);
diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h
index a1651641eb71..e4dffe3f191d 100644
--- a/drivers/infiniband/hw/irdma/verbs.h
+++ b/drivers/infiniband/hw/irdma/verbs.h
@@ -112,6 +112,7 @@ struct irdma_mr {
 	int access;
 	bool is_hwreg:1;
 	bool dma_mr:1;
+	bool is_contig:1;
 	u16 type;
 	u32 page_cnt;
 	u64 page_size;
-- 
2.56.0.385.gd3acb90ef8-goog